Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences related to personal experiences and reflections

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "being" or states of existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phabet
    -0.75
    lap
    -0.69
    opsy
    -0.65
    PsyNetMessage
    -0.64
    rouse
    -0.63
    inav
    -0.63
     Highlands
    -0.60
    ovsky
    -0.60
     fray
    -0.60
     Strait
    -0.59
    POSITIVE LOGITS
     able
    1.12
     judged
    0.83
     aware
    0.81
     bitten
    0.81
     sucked
    0.80
     unable
    0.79
    held
    0.79
     deprived
    0.78
     thankful
    0.78
     immersed
    0.77
    Act Density 0.071%

    No Known Activations